Upload folder using huggingface_hub
Browse files- arcade100k.tiktoken +0 -0
- config.json +52 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +20 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
arcade100k.tiktoken
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./checkpoints/tiny-llava-stablelm-sharegpt4v-unlock-vit-from-12-siglip-stablelm-2-zephyr-1_6b-siglip-so400m-patch14-384-pretrain",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaStablelmForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "stabilityai/stablelm-2-zephyr-1_6b--configuration_stablelm_epoch.StableLMEpochConfig",
|
9 |
+
"AutoModelForCausalLM": "stabilityai/stablelm-2-zephyr-1_6b--modeling_stablelm_epoch.StableLMEpochForCausalLM"
|
10 |
+
},
|
11 |
+
"bos_token_id": 100257,
|
12 |
+
"eos_token_id": 100257,
|
13 |
+
"freeze_mm_mlp_adapter": false,
|
14 |
+
"hidden_act": "silu",
|
15 |
+
"hidden_size": 2048,
|
16 |
+
"image_aspect_ratio": "pad",
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 5632,
|
19 |
+
"max_position_embeddings": 4096,
|
20 |
+
"mm_hidden_size": 1152,
|
21 |
+
"mm_projector_lr": null,
|
22 |
+
"mm_projector_type": "mlp2x_gelu",
|
23 |
+
"mm_use_im_patch_token": false,
|
24 |
+
"mm_use_im_start_end": false,
|
25 |
+
"mm_vision_select_feature": "patch",
|
26 |
+
"mm_vision_select_layer": -2,
|
27 |
+
"mm_vision_tower": "./checkpoints/tiny-llava-stablelm-sharegpt4v-unlock-vit-from-12-siglip-stablelm-2-zephyr-1_6b-siglip-so400m-patch14-384-pretrain/vision_tower",
|
28 |
+
"model_type": "llava_stablelm",
|
29 |
+
"norm_eps": 1e-05,
|
30 |
+
"num_attention_heads": 32,
|
31 |
+
"num_heads": 32,
|
32 |
+
"num_hidden_layers": 24,
|
33 |
+
"num_key_value_heads": 32,
|
34 |
+
"pad_token": "<|endoftext|>",
|
35 |
+
"pad_token_id": 100257,
|
36 |
+
"rope_pct": 0.25,
|
37 |
+
"rope_theta": 10000,
|
38 |
+
"rotary_scaling_factor": 1.0,
|
39 |
+
"tie_word_embeddings": false,
|
40 |
+
"tokenizer_model_max_length": 2048,
|
41 |
+
"tokenizer_padding_side": "right",
|
42 |
+
"torch_dtype": "bfloat16",
|
43 |
+
"transformers_version": "4.37.2",
|
44 |
+
"tune_embed_tokens": false,
|
45 |
+
"tune_entire_model": false,
|
46 |
+
"tune_mm_mlp_adapter": false,
|
47 |
+
"tune_vision_tower": false,
|
48 |
+
"use_cache": true,
|
49 |
+
"use_mm_proj": true,
|
50 |
+
"use_qkv_bias": true,
|
51 |
+
"vocab_size": 100352
|
52 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 100257,
|
4 |
+
"eos_token_id": 100257,
|
5 |
+
"transformers_version": "4.37.2"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ea6d36d10e10fdae9b90f56a961fdde5cb8795ebc26408f5351877d129d18dd
|
3 |
+
size 4097746976
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {},
|
3 |
+
"auto_map": {
|
4 |
+
"AutoTokenizer": [
|
5 |
+
"stabilityai/stablelm-2-zephyr-1_6b--tokenization_arcade100k.Arcade100kTokenizer",
|
6 |
+
null
|
7 |
+
]
|
8 |
+
},
|
9 |
+
"bos_token": "<|endoftext|>",
|
10 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
11 |
+
"clean_up_tokenization_spaces": true,
|
12 |
+
"eos_token": "<|endoftext|>",
|
13 |
+
"errors": "replace",
|
14 |
+
"model_max_length": 2048,
|
15 |
+
"pad_token": "<|endoftext|>",
|
16 |
+
"padding_side": "right",
|
17 |
+
"tokenizer_class": "Arcade100kTokenizer",
|
18 |
+
"unk_token": "<|endoftext|>",
|
19 |
+
"use_fast": false
|
20 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0b2d1ae3e8ec1dc6e381de6be3da19eb867497908fe4afd99a6d386448b2b24
|
3 |
+
size 6715
|